The session was planned with an intension of giving deep exposure in to the course also covering prescribed university syllabus.He started at 10:30A.M with an introduction of resource person
Mr. Hari Phi B.Tech, A Technology expert with strong background in robotics and Artificial intelli _ence innovation through his work as a trainer and CEO of Techie yan Technologies.a research and developiiient organization focused on the latest technologies.
The speaker has discussed about the Basics concepts of Machine Learninqq. The elaborated session has happened with interactive session in between including activities, random questioning.
Topics addressed in Guest Lecture:
- Genetic Algorithms — Motivation, Genetic algorithms, an illustrativ'e example. hypothesis space search, genetic programming, models of evolution and learning, parallelizing genetic algorithms. Learning Sets of Rules — Introduction, sequential covering algorithms. learning rule scts: summary,
learning First-Order rules, learning sets of First-Order rules: FOIL, Induction as inverted
deduction,inverting resolution.
- Introduction, learning with perfect domain theories: PROLOG-EBG, remarks
- Reinforcement Learning — Introduction, the learning task, Q—teaming. non-deterministic. rewards and actions, temporal difference learning, generalizing from examples, relationship to dynamic programming
on explanation-based learning, explanation-based learning of search control know ledge. Analytical Learning-2-Using prior knowledge to alter the search objective. using prior 1‹now1c‹ige to augment search operators.
Combining Inductive and Analytical Learning — Motivation, inductive-ana1y'tica1 approaches to learning, using prior knowledge to initialize the hypothesisObjectives:
- Genetic Algorithms (GAs) are search and optimization techniques inspired by the process of natuial selection and genetics.
Reinforcement Learning (RL) is a type of machine learning where an agent learns to interact w'ith anenvironment to maximize a reward signal.The motivation behind combining inductive and analytical learning is to leverage the strengths of both approaches. Inductive learning focuses on generalizing patterns from data. u'hile analytical learning incorporates prior knowledge to guide the learning process.
Outcomes:
- Students have gotten good awareness regarding Inductive learning.
Students had taken the knowledge for Reinforcement Learning.
Students had grabbed the technology which is based on all Genetic Algorithms.
